Audio chaptering, the task of segmenting long-form audio into coherent sections, is increasingly important for navigating podcasts, lectures, and videos. Despite its relevance, research remains limited and text-based, leaving key questions unresolved about leveraging audio information, handling ASR errors, and transcript-free evaluation. We address these gaps through three contributions: (1) a systematic comparison between text-based models with acoustic features, a novel audio-only architecture (AudioSeg) operating on learned audio representations, and multimodal LLMs; (2) empirical analysis of factors affecting performance, including transcript quality, acoustic features, duration, and speaker composition; and (3) formalized evaluation protocols contrasting transcript-dependent text-space protocols with transcript-invariant time-space protocols. Our experiments on YTSeg reveal that AudioSeg substantially outperforms text-based approaches, pauses provide the largest acoustic gains, and MLLMs remain limited by context length and weak instruction following, yet MLLMs are promising on shorter audio.

翻译：音频章节划分，即将长时音频分割为连贯段落的任务，对于导航播客、讲座和视频日益重要。尽管其具有相关性，相关研究仍局限于文本基础，未能解决关于利用音频信息、处理语音识别（ASR）错误及无文本评估等关键问题。我们通过三项贡献填补这些空白：（1）对基于文本的模型与声学特征、基于学习音频表示的新型纯音频架构（AudioSeg）以及多模态大语言模型（MLLMs）进行系统比较；（2）实证分析影响性能的因素，包括文本质量、声学特征、时长及说话人构成；（3）形式化评估协议，对比依赖文本的文本空间协议与不依赖文本的时间空间协议。我们在YTSeg上的实验表明，AudioSeg显著优于基于文本的方法，停顿提供最大的声学增益，而MLLMs受限于上下文长度及弱指令遵循能力，但在短音频上展现出潜力。